Ai Safety
Topic archive • 2 matches
2026-09-13
Technology
Study links AI written reasoning steps to distinct internal patterns: A new study reveals that reasoning steps such as calculation, formula retrieval, and deduction are clearly separable within an AI model's internal states, particularly in its middle layers.
Artificial Intelligence • The Decoder
Permalink
Investment
OpenAI • OpenAI
Sam Altman rules out OpenAI public offering in 2026: OpenAI CEO Sam Altman confirmed during an interview with Fortune that the company will not go public in 2026, calling such a move ill-advised. During the interview, Altman also discussed recursive self-improvement, a recent Hugging Face hacking incident, and AI safety controls.
Permalink